Gemini 2.5 Pro

by Google DeepMind

Flagship Proprietary Multimodal 🏆 Ranked #6 of 22

85.9

Overall Score

out of 100

About

Google DeepMind's most advanced model, with standout performance in mathematics, science, and long-context reasoning. Gemini 2.5 Pro features a 1 million token context window and an experimental 2 million token mode, alongside strong multimodal capabilities.

Key Metrics

Context Window

1.0M

tokens

Avg Response

1050

milliseconds

Input Cost

$1.25

per million tokens

Output Cost

$10.0

per million tokens

Arena ELO

1380

Chatbot Arena rating

MT-Bench

9.0

out of 10

Benchmark Scores

MMLU

90.0%

HumanEval

87.9%

MATH

91.2%

GPQA

59.1%

MT-Bench

90.0/10

Capability Profile

Strengths & Limitations

Strengths

Limitations

Ideal Use Cases

Model Details

Provider Google DeepMind

Released 2025-03-25

Open source No

Multimodal Yes

Tier Flagship

Global rank #6 / 22

Pricing (USD)

Input tokens $1.25/M

Output tokens $10.0/M

Per 1,000 tokens ≈ $0.0013 input / $0.0100 output

All Benchmarks

MMLU 90.0%

HumanEval 87.9%

MATH 91.2%

GPQA 59.1%

MT-Bench 9.0/10

Arena ELO 1380

Compare this model View leaderboard

Similar Models

You might also consider

OpenAI's most powerful reasoning model, using extended chain-of-thought to tackle the hardest problems in mathematics, science, and coding. o3 sets new standards on GPQA and competitive maths at the cost of higher latency and price.

Anthropic's most powerful and intelligent model, built for the most demanding tasks where quality outweighs cost. Claude Opus 4 leads on complex multi-step reasoning, graduate-level science, and nuanced long-form writing.

The latest and most capable Sonnet model to date. Claude Sonnet 4.6 brings further gains in mathematical reasoning and instruction following, making it Anthropic's most well-rounded model at the Sonnet price point.